Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

fix sharding for generate cache in prefill results #641

Closed
wants to merge 2 commits into from

Conversation

jwyang-google
Copy link
Collaborator

No description provided.

MaxText/maxengine.py Outdated Show resolved Hide resolved
@jwyang-google jwyang-google changed the title remove generate cache from prefill results. fix sharding for generate cache in prefill results May 9, 2024
MaxText/layers/attentions.py Outdated Show resolved Hide resolved
Copy link
Collaborator

@vipannalla vipannalla left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM

MaxText/layers/attentions.py Outdated Show resolved Hide resolved
Copy link
Collaborator

@rwitten rwitten left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

gave an approval but a tiny nit to make the mess smaller. Also can you put a todo with a link to an internal bug explaining the issue.

MaxText/layers/attentions.py Outdated Show resolved Hide resolved
copybara-service bot pushed a commit that referenced this pull request May 10, 2024
PiperOrigin-RevId: 632517062
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

Successfully merging this pull request may close these issues.

None yet

4 participants